Classification of 18F-Florbetaben Amyloid Brain PET Image using PCA-SVM

다국어 초록 (Multilingual Abstract)

Amyloid positron emission tomography (PET) allows early and accurate diagnosis in suspected cases of Alzheimer's disease (AD) and contributes to future treatment plans. In the present study, a method of implementing a diagnostic system to distinguish β-Amyloid (Aβ) positive from Aβ negative with objectiveness and accuracy was proposed using a machine learning approach, such as the Principal Component Analysis (PCA) and Support Vector Machine (SVM). 18F-Florbetaben (FBB) brain PET images were arranged in control and patients (total n = 176) with mild cognitive impairment and AD.
An SVM was used to classify the slices of registered PET image using PET template, and a system was created to diagnose patients comprehensively from the output of the trained model. To compare the per-slice classification, the PCA-SVM model observing the whole brain (WB) region showed the highest performance (accuracy 92.38, specificity 92.87, sensitivity 92.87), followed by SVM with gray matter masking (GMM) (accuracy 92.22, specificity 92.13, sensitivity 92.28) for Aβ positivity. To compare according to per-subject classification, the PCA-SVM with WB also showed the highest performance (accuracy 89.21, specificity 71.67, sensitivity 98.28), followed by PCA-SVM with GMM (accuracy 85.80, specificity 61.67, sensitivity 98.28) for Aβ positivity. When comparing the area under curve (AUC), PCA-SVM with WB was the highest for per-slice classifiers (0.992), and the models except for SVM with WM were highest for the per-subject classifier (1.000). We can classify 18F-Florbetaben amyloid brain PET image for Aβ positivity using PCA-SVM model, with no additional effects on GMM.

참고문헌 (Reference)

1 강현, "VGG-based BAPL Score Classification of 18F-Florbetaben Amyloid Brain PET" 대한의생명과학회 24 (24): 418-425, 2018

2 Segovia F, "Using CT data to improve the quantitative analysis of 18F-FBB PET neuroimages" 10 : 158-, 2018

3 Moćkus J, "The Application of Bayesian Methods for Seeking the Extremum: Toward global optimization 2" Elsevier 117-, 1978

4 Illán IA, "The Alzheimer's Disease Neuroimaging Initiative" 181 : 903-916, 2011

5 Piramal Imaging Limited, "Summary of product characteristics" Piramal Imaging Limited 2014

6 Haass C, "Soluble protein oligomers in neurodegeneration: lessons from the Alzheimer's amyloid β-peptide" 8 : 101-, 2007

7 Lopresti BJ, "Simplified quantification of Pittsburgh Compound B amyloid imaging PET studies: a comparative analysis" 46 : 1959-1972, 2005

8 Lundeen TF, "Signs and artifacts in Amyloid PET" 38 : 2123-2133, 2018

9 Pedregosa F, "Scikit-learn: machine learning in python" 12 : 2825-2830,

10 Bergstra J, "Random search for hyper-parameter optimization" 13 : 281-305, 2012

11 Platt J, "Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods" 10 : 61-74, 1999

12 Oh IS, "Pattern recognition" Kyobobook 137-173, 2008

13 Bullich S, "Optimized classification of 18F-Florbetaben PET scans as positive and negative using an SUVR quantitative approach and comparison to visual assessment" 15 : 325-332, 2017

14 Tamil Iniyan Gunasekaran, "MicroRNAs as Novel Biomarkers for the Diagnosis of Alzheimer's Disease and Modern Advancements in the Treatment" 대한의생명과학회 21 (21): 1-8, 2015

15 Brucher N, "Measurement of inter- and intra-observer variability in the routine clinical interpretation of brain 18-FDG PET-CT" 29 : 233-239, 2015

16 Snoek J, "In Advances in Neural Information Processing System" 2951-2959, 2012

17 Seibyl J, "Impact of training method on the robustness of the visual assessment of 18F-Florbetaben PET scan: results from a phase-3 study" 57 : 900-906, 2016

18 Gonçalves AB, "Feature extraction and machine learning for the classification of Brazilian savannah pollen grains" 11 : e0157044-, 2016

19 Chaves R, "FDG and PIB biomarker PET analysis for the Alzheimer's disease detection using Association Rules" s2576-s2579, 2012

20 Gulshan V, "Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs" 316 : 2402-2410, 2016

21 Lakhani P, "Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks" 284 : 574-582, 2017

22 Taylor JC, "Comparison of machine learning and semiquantification algorithms for (I123) FP-CIT classification: the beginning of the end for semi-quantification?" 4 : 29-, 2017

23 DeLong ER, "Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach" 44 : 837-845, 1988

24 Barthel H, "Cerebral amyloid-β PET with florbetaben (18F) in patients with Alzheimer's disease and healthy controls: a multicenter phase 2 diagnostic study" 10 : 424-435, 2011

25 Blanc-Durand P, "Cerebral 18F-FDG PET in macrophagic myofasciitis: An individual SVM-based approach" 12 : e0181152-, 2017

26 Xue DX, "CNN-SVM for microvascular morphological type recognition with data augmentation" 36 : 755-764, 2016

27 Varma S, "Bias in error estimation when using crossvalidation for model selection" 7 : 91-, 2006

28 Choi WH, "Automated quantification of amyloid positron emission tomography: a comparison of PMOD and MIMNEURO" 30 : 682-689, 2016

29 Zhang Y, "A hybrid method for MRI brain image classification" 38 : 10049-10053, 2011

30 Sherman M, "A comparison between bootstrap methods and generalized estimating equations for correlate outcomes in generalized linear models" 26 : 901-925, 1997

31 Vapnik VN, "10.5 Support Vector Machine: Statistical Learning Theory" Wiley-Interscience 421-441, 1998